WO2020247664A1 - Procédés et systèmes permettant d'analyser des images d'un brûleur de torche - Google Patents

Procédés et systèmes permettant d'analyser des images d'un brûleur de torche Download PDF

Info

Publication number
WO2020247664A1
WO2020247664A1 PCT/US2020/036169 US2020036169W WO2020247664A1 WO 2020247664 A1 WO2020247664 A1 WO 2020247664A1 US 2020036169 W US2020036169 W US 2020036169W WO 2020247664 A1 WO2020247664 A1 WO 2020247664A1
Authority
WO
WIPO (PCT)
Prior art keywords
smoke
interest
regions
flare burner
flare
Prior art date
Application number
PCT/US2020/036169
Other languages
English (en)
Inventor
Kurt Edward KRAUSE
Matthew Martin
Tobias Nebel
Michael Kon Yew Hughes
Frank M. Haran
Sebastien Tixier
James W. Harris
Original Assignee
Honeywell International Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Honeywell International Inc. filed Critical Honeywell International Inc.
Publication of WO2020247664A1 publication Critical patent/WO2020247664A1/fr

Links

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
    • F23G—CREMATION FURNACES; CONSUMING WASTE PRODUCTS BY COMBUSTION
    • F23G7/00—Incinerators or other apparatus for consuming industrial waste, e.g. chemicals
    • F23G7/06—Incinerators or other apparatus for consuming industrial waste, e.g. chemicals of waste gases or noxious gases, e.g. exhaust gases
    • F23G7/08—Incinerators or other apparatus for consuming industrial waste, e.g. chemicals of waste gases or noxious gases, e.g. exhaust gases using flares, e.g. in stacks
    • F23G7/085—Incinerators or other apparatus for consuming industrial waste, e.g. chemicals of waste gases or noxious gases, e.g. exhaust gases using flares, e.g. in stacks in stacks
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
    • F23N—REGULATING OR CONTROLLING COMBUSTION
    • F23N5/00—Systems for controlling combustion
    • F23N5/003—Systems for controlling combustion using detectors sensitive to combustion gas properties
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
    • F23N—REGULATING OR CONTROLLING COMBUSTION
    • F23N5/00—Systems for controlling combustion
    • F23N5/02—Systems for controlling combustion using devices responsive to thermal changes or to thermal expansion of a medium
    • F23N5/10—Systems for controlling combustion using devices responsive to thermal changes or to thermal expansion of a medium using thermocouples
    • F23N5/102—Systems for controlling combustion using devices responsive to thermal changes or to thermal expansion of a medium using thermocouples using electronic means
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
    • F23N—REGULATING OR CONTROLLING COMBUSTION
    • F23N5/00—Systems for controlling combustion
    • F23N5/16—Systems for controlling combustion using noise-sensitive detectors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
    • F23G—CREMATION FURNACES; CONSUMING WASTE PRODUCTS BY COMBUSTION
    • F23G2209/00—Specific waste
    • F23G2209/14—Gaseous waste or fumes
    • F23G2209/141—Explosive gases
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
    • F23N—REGULATING OR CONTROLLING COMBUSTION
    • F23N2225/00—Measuring
    • F23N2225/08—Measuring temperature
    • F23N2225/10—Measuring temperature stack temperature
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
    • F23N—REGULATING OR CONTROLLING COMBUSTION
    • F23N2229/00—Flame sensors
    • F23N2229/20—Camera viewing
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F23—COMBUSTION APPARATUS; COMBUSTION PROCESSES
    • F23N—REGULATING OR CONTROLLING COMBUSTION
    • F23N2241/00—Applications
    • F23N2241/18—Incinerating apparatus

Definitions

  • This invention relates generally to processes and systems that analyze images of a flare burner to determine the apparent presence of absence of smoke.
  • flare burner In process industries such as petroleum (oil) refineries and petrochemical plants, it is a common practice to bum the exhaust gases of a stage of the refinery or plant before releasing the gases to the atmosphere in order to reduce the environment pollution using a device known as a flare or flare burner in a process known as flaring or flare burning.
  • the flare burner may be a steam-assisted, combustible gas assisted, or air assisted flare burner.
  • Flaring is commonly used in the petrochemical and oil industry as a combustion process to safely dispose of flammable waste gases produced from normal operations, as well as during, emergency process upsets process start-up, process shutdown, and turnaround operations. Flaring helps prevent the undesired release of the hydrocarbons in the waste gases into the atmosphere.
  • combustion of hydrocarbons is seldom 100% complete leading to black smoke (hereafter“smoke”) production due to inefficient combustion of the hydrocarbons which can result in significant financial costs including fines from regulatory bodies and costs due to steam and pressurized air usage.
  • Regulatory authorities e.g., the U.S. Environmental Protection Agency (EPA) generally impose environmental regulations in terms of monitoring and controlling smoke. In general smoke reduction has the highest priority, but in locations where the refineries are located relatively close to residential communities, noise reduction can be important too. Failure to adhere to EPA or other regulations can result in the imposition of serious financial penalties and sometimes revoking of operating licenses for the owner of the process.
  • EPA U.S. Environmental Protection Agency
  • the operators may track and record: 1) the presence and absence of smoke, 2) the presence and absence of the flare flame, 3) the flow rate and composition of flare gas, 4) the flow rate and composition of assist fuel gas, purge gas, steam and/or air, 5) calculated values for net heating value at regular intervals in time based on the above listed input parameters, and 6) the time duration of flaring and smoking events. While failure to comply with the recording or performance aspects of flare operation can result in significant fines, operating too conservatively with too much assist fuel gas, purge gas, steam, or air results in excessive operation utility costs. Accordingly, it is desirable to utilize a flare monitoring system.
  • flare monitoring and control device or system The main role of a flare monitoring and control device or system is to monitor and measure certain parameters of the flare such as amount/volume of the smoke, size of the flare, and noise level (typically in dB), and take certain countermeasures to control the flare so as to ensure compliance with EPA smoke and noise level regulations.
  • dB noise level
  • One or more methods for monitoring a flare burner with a video camera have been invented which can be used in a system for observing and controlling a flare.
  • the present invention provides methods and systems which may indicate to operators the presence or absence of one or more of smoke, flare flame, and steam plume and record those indications or measurements. Additionally, the methods and systems may confirm whether compliance with local regulations on visual emissions, smoke plume is achieved. In various aspects and embodiments, the methods and systems automatically adjust the delivery rate of key inputs including assist fuel gas, purge gas, steam, and/or air simultaneously to maintain or attain compliance with said local regulatory requirements.
  • the present invention may be characterized, in at least one aspect, as providing a process for determining an apparent presence or absence of smoke from a flare burner associated with a processing plant by: a) obtaining a visual image of the flare burner and an area surrounding the flare burner; b) analyzing the visual image by segmenting the visual image into a plurality of regions of interest, and, calculating a smoke index for each of the regions of interest based on a historical intensity of a plurality of pixels within each of the regions of interest; c) determining the apparent presence of smoke based on the smoke index for the regions of interest by comparing the smoke index to a threshold smoke index level; and, d) indicating the apparent presence of smoke for the regions of interest when the smoke index is at or above the threshold smoke index level.
  • the smoke index of the pixels may be calculated by determining an intensity value for one or more pixels in a particular region of interest by subtracting a background intensity value, wherein the background intensity value of each pixel is a maximum intensity value for that pixel from a series of visual images.
  • the smoke index may be based on an opacity determination.
  • the smoke index of each region of interest is calculated with an equation comprising, 100%
  • INTnow represents an average intensity value of one or more pixels in a particular region of interest
  • INTbackground represents a maximum intensity value for the one or more pixels in the particular region of interest determined from a series of visual images.
  • the series of visual images may be, for example, between 20 to 70 frames preceding the visual image.
  • One of ordinary skill in the art will appreciate and understand that other numbers of previous images may be used, and that the previous images need immediately precede the current image.
  • the intensity value may be a color intensity value.
  • the regions of interest move in relation to the flare burner.
  • the regions of interest may be static in relation to the flare burner.
  • the process may also include adjusting at least one process condition of the processing plant based on a difference between the smoke index is at or above the threshold smoke index level and, repeating steps a) - c).
  • the at least one process condition may be adjusted to maintain the smoke index at the predetermined set point.
  • the steps a) - c) may be repeated until the smoke index reaches a predetermined level.
  • the process may further include calculating a reliability value for each smoke index calculated. Additionally, the process may include increasing a weighting to non-camera based values used for determining the smoke index based on the reliability values.
  • the process includes obtaining a current process condition information of the processing plant and when a number of the calculated smoke indexes with a reliability value above a predetermined level is below a minimum amount, the process includes determining the apparent presence by comparing the current process condition information with a database having process condition data and apparent smoke probability associated with the process condition data. It is further contemplated that the process includes obtaining a current atmospheric condition information at the flare burner; and, when a number of the calculated smoke indexes with a reliability value above a predetermined level is below a minimum amount, the process includes determining the apparent presence by comparing the atmospheric condition information with the database, wherein the database further comprises having atmospheric condition data and apparent smoke probability associated with the atmospheric condition data.
  • the process may include obtaining an audio signature of the flare burner corresponding to the visual image, and the smoke index for each regions of interest may be calculated based on the audio signature.
  • the process may include obtaining an UV image of the flare burner corresponding to the visual image, and the smoke index for each regions of interest may be calculated based on the UV image. [00019] The process may include: obtaining a temperature at a predetermined position spaced from the flare burner corresponding to the visual image, comparing the temperature to a threshold temperature, and performing an action when the temperature meets or passes the threshold temperature.
  • the present invention may be generally characterized as providing a process for determining an apparent presence or absence of smoke from a flare burner associated with a processing plant by: obtaining a plurality of visual images of the flare burner and an area surrounding the flare burner, wherein the plurality includes an image with no smoke and an image with smoke, and wherein the presence or absence of smoke has been predetermined; analyzing the visual image by segmenting the visual image into a plurality of regions of interest, and, calculating a smoke index for each of the regions of interest based on a historical intensity of a plurality of pixels within each of the regions of interest; determining the apparent presence of smoke based on the smoke index for the regions of interest by comparing the smoke index to a threshold smoke index level; and, comparing the determination with the predetermined presence or absence of smoke with the image.
  • the present invention may also be broadly characterized, in a third aspect as providing a system for monitoring a flare burner associated with a processing plant and configured to receive a gas to be combusted, the system configured to determine an apparent presence or absence of smoke from the flare burner, the system including: at least one camera configured to obtain images of the flare burner and an area surrounding the flare burner; and, a controller in communication with the camera and configured to: receive the visual image of the flare burner; and, analyze the visual image by: segmenting the visual image into a plurality of regions of interest; and, calculating a smoke index for each of the regions of interest based on a historical intensity of a plurality of pixels within each of the regions of interest; and, determine the apparent presence of smoke based on the smoke index for the regions of interest by comparing the smoke index to a threshold smoke index level; and, indicate the apparent presence of smoke for the regions of interest when the smoke index is at or above the threshold smoke index level.
  • Figure 1 shows a schematic view of a system according to one or more aspects of the present disclosure
  • Figure 2 shows a process flow diagram according to one or more aspects of the present disclosure
  • Figure 3 shows an analyzed image according to one or more aspects of the present disclosure
  • Figure 4 shows another analyzed image according to one or more aspects of the present disclosure
  • Figure 5 shows a graphical comparison according to one or more aspects of the present disclosure.
  • Figure 6 shows a graphical comparison according to one or more aspects of the present disclosure.
  • a system 10 includes one or more cameras 12 obtaining visual images of a flare burner 14.
  • the flare burner 14 receives a stream of waste gas 16 to be combusted in a flame 18 at the outlet of the flare burner 14. Additionally, the flare burner may receive a stream of assist gas 20, as well as a stream of steam 22.
  • the field of view 23 of the cameras 12 preferably include areas around the flare burner 14 and the flame 18. Accordingly, the cameras 12 preferably provide a generally wider field of view. By using a wider field of view and including the area around the flare burner 14 and the flame 18, it is believed to be easier to determine the presence or absence of smoke. While a single camera 12 is the primary approach used by many current flare burner monitoring systems, the use of using multiple cameras 12 allows simultaneous capture of both local images and wider views for signal processing and usable views in cases where wind direction may prevent a certain camera from being able to see the exhaust and smoke plume.
  • the camera 12 may include single lens camera, zooming functions, wide angle high definition (HD) camera and any camera technology available for both optical zoom and digital zooming functions.
  • the human machine interface will allow the operator to adjust their views to better understand the differences between the video images and the analytics images. This will build confidence for the operators that the analytics are providing the correct information.
  • the cameras 12 are in communication with one or more controllers 24 that each include at least one processor and memory storing computer-readable instructions that, when executed by the at least one processor, cause the one or more controllers 24 to perform a process that may include one or more steps.
  • the controller 24 may be an Application Specific Integrated Circuit (ASIC), an electronic circuit, memory (shared, dedicated, or group) and/or a computer processor (shared, dedicated, or group) that executes one or more executable instructions (e.g., software or firmware programs) stored on the memory, a combinational logic circuit, and/or other suitable components that provide the described functionality. While this disclosure includes particular examples and arrangements of the units, the scope of the present system is not so limited, since other modifications will become apparent to the skilled practitioner.
  • ASIC Application Specific Integrated Circuit
  • the controller 24 is further configured to obtain, receive, and/or send information over a communication network (e.g., local communication network, the internet, an intranet). Specifically, the controller 24 may receive signals and/or parameters via the communication network. The controller 24 may display (e.g., in real time, with a short delay, with a long delay) performance information related to the received signals and/or parameters on an interactive display device 26 (i.e., display screen), which may be accessible to an operator or user, either locally or over a communication network like the internet. Additionally, the controller 24 is configured to receive input, via, a keyboard, touch screen, mouse, other device.
  • a communication network e.g., local communication network, the internet, an intranet
  • the controller 24 may display (e.g., in real time, with a short delay, with a long delay) performance information related to the received signals and/or parameters on an interactive display device 26 (i.e., display screen), which may be accessible to an operator or user, either locally or over a communication network like the internet
  • the controller 24 may be configured to receive, from one or more cameras 12, data related to images obtained of the flare burner 14 and the area surrounding the flare burner 14.
  • the controller 24 is configured to analyze the obtained images and determine, for example, the likelihood that the flame 18 is producing smoke 28. Based on the determination, the controller 24 may be configured to determine one or more recommended adjustments to one or more process conditions described herein. Additionally, the determination can be outputted to the display device 26. However, the determination by the controller 26 preferably incorporates more information than just the obtained images.
  • the controller(s) 24 is in communication with other sensors that provide information or data to the controller to be used when analyzing the images and determining the likelihood that the flare is producing smoke.
  • sensors may include, but are not limited to, pressure sensors, differential pressure sensors, other flow sensors, temperature sensors including thermal cameras and skin thermocouples, capacitance sensors, weight sensors, gas chromatographs, moisture sensors, ultrasonic sensors, position sensors, timing sensors, vibration sensors, level sensors, liquid level (hydraulic fluid) sensors, and other sensors commonly found in the refining and petrochemical industry.
  • process laboratory measurements may be taken using gas chromatographs, liquid chromatographs, distillation measurements, octane measurements, and other laboratory measurements.
  • System operational measurements also can be taken to correlate the system operation to the equipment measurements.
  • sensors may include transmitters and deviation alarms. These sensors may be programmed to set off an alarm, which may be audible and/or visual.
  • the controller 24 may be in communication with one or more sensors 30a, 30b, 30c for obtaining process condition information associated with the processing plant, such as flow rate, gas composition, temperature, to name a few.
  • the controller 24 may be in communication with sensors 32a, 32b, 32c in the lines, for example, providing the streams 16, 20, 22 discussed above.
  • the controller 24 may be in communication with valves 34a, 34b, 34c in the lines providing the streams 16, 20, 22 so that the flow of the streams 16, 20, 22 can be adjusted (discussed below).
  • the controller 24 may also be in communication with sensors 36a, 36b, 36c that obtain atmosphere condition information at the flare burner, such as, air temperature, humidity, pressure, wind speed, direction, sun position, rain, etc.
  • the controller 24 may also be in communication with an ultraviolet (UV) camera 38 that is configured to provide UV images of the flare burner 14.
  • UV camera 38 can be used to provide a number of additional parameters. For instance, a UV camera 38 can easily discriminate against sunlight which might otherwise interfere with measurements.
  • the utility of the UV camera 38 can be enhanced with spectral filters - for instance to determine individual chemical species. For example, sulphur dioxide is an important pollutant. The identification and quantification of this species can be made with well-known UV techniques. Other species can be identified with similar techniques.
  • the controller 24 may also be in communication with a microphone 40 for providing audio data associated with the flare burner 14. Audio signatures of wind may be included in the raw data and may need to be removed as part of the image processing procedure. After removing wind signatures, the resulting audio may provide an indication that the flare burner 14 is releasing a vapor stream, burning the waste gases, having a steam release, or harmonically oscillating over these various conditions.
  • the controller 24 may also be in communication with a thermocouple 42 that is configured to measure a temperature a fixed distance from the flare burner 14 or the flame 18. As conditions change at the flare burner 14 tip, the temperature at the thermocouple 42 will change and can alert the operator to focus on the audio and visual signals to determine if changes to the flare operation are required.
  • a temperature signature around the flare burner 14 may also be utilized, for example by measuring temperature on the piping, at the tip of the flare burner 14, and at the specific distance away from the tip that has a definitive temperature change as the vent streams changes to different modes of operation— full event, small flame, or steam purge. This could be some distance away from the flare burner 14 and still have a measurable change.
  • the network connections depicted include a local area network (LAN) and a wide area network (WAN), and a wireless telecommunications network, but may also include other networks and communication methods.
  • LAN local area network
  • WAN wide area network
  • wireless telecommunications network a wireless telecommunications network
  • the components of the system 10 may be connected to the LAN through a network interfaces or adapters.
  • the components of the system 10 may be connected through modems or other means for establishing communications over the WAN, such as to an external network (e.g., the Internet).
  • the components of the system 10 may include one or more transceivers, digital signal processors, and additional circuitry and software for communicating with each other in the wireless network.
  • network connections shown are illustrative and other means of establishing a communications link between the computers may be used.
  • the existence of any of various network protocols such as TCP/IP, Ethernet, FTP, HTTP and the like, and of various wireless communication technologies such as GSM, CDMA, Wi-Fi, and WiMAX, is presumed, and the various components described herein may be configured to communicate using any of these network protocols or technologies.
  • the controller 24 receives information and data from the various sensors and data collecting devices of the system 10 and is configured to determine one or more of the following: the presence or absence of a flame 18; the presence or absence of smoke plume 28 associated with the flame 18; and the presence or absence of steam plume associated with the flame 18. Additionally, the controller 24 should be configured to indicate and differentiate between smoke and steam. [00043] In addition to the foregoing indications, the controller 24 may also be configured to provide a reliability value indicating a level of confidence in the above listed indications.
  • a dark night sky while there may be a high confidence and high reliability value in identifying the presence of flame, there may be a low level of confidence, and thus low reliability value, differentiating between soot and sky background.
  • white steam from a flare tip looks dark or like soot, especially when presented on a background of dark, overcast clouds. Accordingly, in such a situation, the controller 24 may provide a low confidence indication in determining whether the steam plume is indeed steam or is soot, smoke.
  • the confidence level may be indicated with a high/low or good/bad indication, with a high, medium, low, or with a numerical scale, for example from 1-10.
  • the controller 24 may be in communication with a database 44 so that the controller 24 can store and retrieve information, including, for example, historical data from the various sensors and measuring devices including flare gas, assist fuel gas, assist steam or air flow pressures, rates and compositions; indications of presence or absence of flare pilot or main flame from other devices such as flame scanners, thermocouples or flame ionization rods and/or environmental and weather conditions.
  • the controller 24 may also record the time (timestamp) of the onset and the stopping of the presence and absence of flame and thereby the duration time/dissipation rate of either or both smoke and/or flame. With the time of start, end and duration of smoke or flame events, the controller 24 will generate a record of events for reporting to local regulators and for calculating whether the operation is in or out of compliance with locally applied regulations. For example, some jurisdictions may limit smoking to no more than five minutes duration in a two-hour time frame. The controller 24 may be programmed to determine whether the operation is within or outside local regulatory limits. In addition, the controller 24 may cause an alarm to be triggered or a report to be automatically generated.
  • the controller 24 is configured to record the determined events in the database 44, along with all of the different variables used and data points collected. These results can be reviewed by an expert to confirm accuracy of the results as discussed below to be used in a machine learning process to train the controller 24 or another controller. [00047] Moreover, based on inputs available in low visibility, low contrast lighting such as at night or in fog or clouds, the controller 24 can access the database 44 to determine the presence or absence of smoke and/or flame based on similar conditions to the current conditions, preferably when confidence or reliability values are low.
  • the controller 24 may indicate a high confidence in smoke/no smoke based on a comparison of the current variables and historical variables.
  • the controller 24 may be further configured to adjust process conditions so that the system is operating at a certain set point.
  • the incipient smoke point the operating condition just before the onset of smoke, is understood in the industry to correspond to the highest destruction efficiency, combustion of the highest percentage of hydrocarbons in and by the flare flame at the point where assist fuel assist gas, steam and/or air are minimized to just lower than the levels which who produce smoke from the flare flame.
  • the controller 24 may be configured to analyze the images and determine what conditions are at or just below the incipient smoke level and adjust various aspects of the processing plant so that the system is at the incipient smoke level. For example, the controller 24 may adjust flow rate with the valves 34a, 34b, 34c.
  • a process flow diagram depicts various steps of one process 100 that may be implemented by the system 10.
  • the process 100 includes obtaining images 102, analyze images 104, determining smoke index 106, comparing smoke index to threshold smoke index level 108, indicating the presence of smoke 110, and, taking an action 112.
  • the step 102 of obtaining a visual image preferably includes obtaining a stream of images/video coming from the camera 12, which is at least one visual/NIR camera, pointed at the flare burner 14.
  • the camera 12 is positioned sufficiently far away from the flare burner 14 to record an image of the flame 18 at the flare burner 14, as well as several flame-lengths of background (BG) around the flame 18.
  • the camera 12 may employ a zoom lens (or multiple cameras with different lenses) to capture large differences in flame 18 size (turn-down ratios 10 5 ).
  • a high-resolution camera(s) 12 might be employed with automatically controlled regions of interest (discussed below) and/or resolution(s) (by combining pixels).
  • One reason is believed to be beneficial to use variable length scales is that smoke dissipation can be expected to occur on similar length scales to the flame 18 length.
  • a camera 12 may be poorly situated. If the smoke plume 28 is blowing away from the camera 12, the plume 28 may be partially obscured by the flame 18 or the flare burner 14, or the opacity of the plume 28 may be artificially magnified because the camera 12 sees an artificially increased optical path length.
  • two or more cameras 12 are employed and placed at regular intervals, with the two cameras 12 separated by 90 degrees.
  • the processor 24 can determine which camera 12 has the best cross section view of the plume 28 and this camera 12 is selected for analyzing the images from same.
  • cameras 12 may be used together to put calculated variables into absolute distance scales. For instance, an absolute distance to where the smoke becomes non-visible could be determined and possibly controlled.
  • the controller 24 performs an image analysis in order to determine the presence or absence of smoke 28 at the flare burner 14.
  • the image analysis may optionally include performing an image segmentation (for example color segmentation) and determine where the flame 18 is and where the tip of the flare burner 14 is. Then, the image analysis defines regions of interest (ROIs) or boxes to divide the image into regions of smoke / BG / flame / flare / clouds.
  • ROIs regions of interest
  • This definition can happen in multiple ways: static segmentation of the image into reasonably-sized ROIs; dynamic segmentation of the image into ROIs centered around and moving with the current flame-tip (this is advantageous to minimize computing power required as the smoke plume is expected to extend in the same direction roughly as the flame); or dynamic segmentation according to image segments like smoke, flame, sky, clouds, steam, etc.
  • the image analysis step 104 includes determining a background image. This background has the effects of smoke minimized.
  • the following procedure is performed. First, the color image is reduced to an intensity scale and the color image is intended to include black/white/grey images and intensities. This can be done by creating a linear or non-linear combination of the color channels, or simply by taking a single channel. Based on experimental results, using the blue channel of an RGB (red, green, and blue) representation removes smoke from the image in an acceptable manner. Then, a maximum intensity value of each pixel (or group of pixels, depending on level of analysis performed) in said intensity representation is made using the last X number frames.
  • RGB red, green, and blue
  • fps frames-per-second
  • fps frames-per-second
  • Another value could be chosen (e.g. the median, the most populated, the value 1 sigma above the mean, and others).
  • the background i.e. the clouds
  • this background determination can happen in a moving ROI that moves with the background. Affine transformations of the clouds might be included to account for shape changes.
  • the motion of the clouds can be calculated independently of the smoke motion by looking at the part of the image in which smoke is not present.
  • the background determination may also be accomplished through the use of databases (e.g. Clear sky library) or with the International Commission on Illumination (CIE) standard calculation for sky intensity based on Earth’s position, time, and sighting direction.
  • databases e.g. Clear sky library
  • CIE International Commission on Illumination
  • the process includes the step 106 of calculating a smoke-index for each ROI. In in exemplary calculation, this is determined by Equation (1):
  • the smoke-index is a percentage-level number that is equal to one hundred times one minus the summed intensity of the current image divided by the summed intensity of the background ROI.
  • a low level means no smoke. It is also contemplated that smoke-index is calculated differently (e.g. the difference of intensity values (background - current) normalized to the background intensity).
  • the background and current intensity can be adequately filtered: e.g. by fitting a smooth polynomial.
  • the size of the ROI has to be chosen well. It is believed that this calculation does not work well on a single pixel basis - a single pixel or regions which are too small are too sensitive to such things as small cloud motions. Thus, it has been determined that ROI sizes from 1 ⁇ 4 to 1 flame-area size seem to work well to filter out small scale variations.
  • every ROI can be assigned a value for the smoking- index.
  • These specific smoke index levels can be displayed on the display screen with the image of the flare burner, such as shown in FIG. 3, in which a first set of ROIs 200 have no smoke, and a second set have been determined to have smoke 202.
  • One of the ROIs or a defined subset of the ROIs will then be chosen to perform the step 108 of comparing those index numbers with a threshold value smoke index.
  • the threshold value smoke index is threshold smoke index is the minimum index a trained observer would indicate that smoke was present and can be a fluid value.
  • the database can be consulted for determining the threshold value smoke index.
  • the process includes the step 110 of providing an indication of the presence or absence of smoke based on the comparison of the index numbers with the threshold values.
  • Choosing the correct ROI(s) can be based on geometrical information (flame direction) and/or on further segmentation / cross correlation with other parameters such as absolute intensity / entropy / frequency content / etc. It is known that smoke levels will become smaller as the plume 28 moves further from the flame 18. It is believed to be advantageous to not control on a maximum smoke level, but on a smoke level a fixed distance, or a fixed number of flame lengths away from the tip of the flare burner 14. Alternatively, as discussed above, it may be desirable to determine at what smoke index the smoke is no longer deemed to be visible and then to control the flare burner 14 to produce that smoke index at a predetermined distance from the flare. Of course, the smoke- index number can change rapidly and randomly therefore it is envisioned that considerable time smoothing will have to be employed.
  • a confidence number, also determined by the controller 24, for the overall smoke-index provides an indication of how reliable the obtained smoke index values are.
  • the step of determining the smoke index 106 can apply a greater weight to non- visual based variables to provide a more accurate determination.
  • the analysis may include comparing current conditions with similar conditions in the database and relying the determination in the database to indicate whether or not smoke is present.
  • the present invention also contemplates using a machine leaming/neural network system to determine smoke visibility.
  • the images used in the first step 102 of the process may not be real time images but representative images and video samples of flares. Some of the images exhibit a low level of visible smoking, as well as images have no visible smoke, and those that include high levels of smoke. It is believed to be advantageous to have a frame rate fast enough that smoke cannot transition between non-adjacent regions of interest between frames, but slow enough that there is not a large overhead of non-relevant information to process. In experiments, rates between 5 and 30 frames per second are preferred and about 10 fps is most preferred ideal.
  • the region of interest (ROI) with respect to the flare burner are defined in the various images. Again, it is preferred that the image is not just of the flare burner and/or the flame, but of three to five times the maximum expected flame length.
  • the regions of interest may be fixed with respect to the camera field of view, or they can translate with the flare. Translating regions of interest may be advantageous for reducing the required computing power, or for eliminating regions where calculations are difficult, such as where the sun saturates the image.
  • the regions of interest cannot be too small or too large. Too small and the movement of clouds will affect the measurements, and too large smoke which does not occupy the entire ROI will not have enough of an impact on the statistics for the entire region of interest.
  • regions of interest of 2500 to 10000 pixels are possible. Also, it is believed to be preferred to have 20 to 50 regions of interest in each frame as the smoke determination is dynamic with this technique. At least a third of the regions of interest should represent background regions with no smoke. The other regions can be compared to these.
  • Some key features include use of general-purpose cameras which result in a low cost. Also advanced video analysis such as background image cleaning for atmospheric conditions including high sunlight, low light, humidity, and background gas issues is used to enhance the models used to deliver the recommendations.
  • the system will be trained, and the results of the training shall be encoded into the production system.
  • a training data set must be created.
  • the possible classifications for each ROI should be ‘no-smoke’ 200,‘smoke’ 202, and‘unknown’ 204. See FIG 4.
  • the unknown ROIs 204 should be weighted accordingly when determining the merit figures for the neural network.
  • the flare being tested is not in the field of view.
  • two ROIs with smoke 202 are indicated, and one ROI with unknown 204 is indicated. This determination is not completely evident in a single frame; but is more evident as the video is played back as the smoke can be seen to move against the background.
  • raw opacity calculated with a current frame comparison of blue intensity to a maximum pixel representation over the last, for example, 30 frames, which is displayed in green text, is not always an acceptable indicator of the presence of smoke.
  • FIGS. 5 and 6 show four variables calculated from these regions of interest along with similar calculations from 10 other video clips. These variables were input into a MatLab neural network Pattern Recognition tool (nprtool) which provided a useable model and showing proof of concept that the smoke index can be determined by comparison with a historical value (average (FIG. 5) or standard deviation (FIG. 6)).
  • nprtool MatLab neural network Pattern Recognition tool
  • the network can be taken and configured as part of the controller 24 to output a smoke indication, along with a measurement uncertainty for the system 10.
  • any of the above lines, conduits, units, devices, vessels, surrounding environments, zones or similar may be equipped with one or more monitoring components including sensors, measurement devices, data capture devices or data transmission devices. Signals, process or status measurements, and data from monitoring components may be used to monitor conditions in, around, and on process equipment. Signals, measurements, and/or data generated or recorded by monitoring components may be collected, processed, and/or transmitted through one or more networks or connections that may be private or public, general or specific, direct or indirect, wired or wireless, encrypted or not encrypted, and/or combination(s) thereof; the specification is not intended to be limiting in this respect.
  • Signals, measurements, and/or data generated or recorded by monitoring components may be transmitted to one or more computing devices or systems.
  • Computing devices or systems may include at least one processor and memory storing computer- readable instructions that, when executed by the at least one processor, cause the one or more computing devices to perform a process that may include one or more steps.
  • the one or more computing devices may be configured to receive, from one or more monitoring component, data related to at least one piece of equipment associated with the process.
  • the one or more computing devices or systems may be configured to analyze the data. Based on analyzing the data, the one or more computing devices or systems may be configured to determine one or more recommended adjustments to one or more parameters of one or more processes described herein.
  • the one or more computing devices or systems may be configured to transmit encrypted or unencrypted data that includes the one or more recommended adjustments to the one or more parameters of the one or more processes described herein.
  • a first embodiment of the invention is a process for determining an apparent presence or absence of smoke from a flare burner associated with a processing plant, the process comprising a) obtaining a visual image of the flare burner and an area surrounding the flare burner; b) analyzing the visual image by segmenting the visual image into a plurality of regions of interest; and, calculating a smoke index for each of the regions of interest based on a historical intensity of a plurality of pixels within each of the regions of interest; and, c) determining the apparent presence of smoke based on the smoke index for the regions of interest by comparing the smoke index to a threshold smoke index level; and, d) indicating the apparent presence of smoke for the regions of interest when the smoke index is at or above the threshold smoke index level.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, wherein the smoke index of the pixels are calculated by determining an intensity value for one or more pixels in a particular region of interest by subtracting a background intensity value, wherein the background intensity value of each pixel comprises a maximum intensity value for that pixel from a series of visual images.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, wherein the smoke index is based on an opacity determination.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, wherein the smoke index of each region of interest is calculated with the following equation, 100% * (1-INTnow/INTbackground), wherein INTnow represents an average intensity value of one or more pixels in a particular region of interest, and wherein INTbackground represents a maximum intensity value for the one or more pixels in the particular region of interest determined from a series of visual images.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, wherein the series of visual images comprises between 20 to 70 frames preceding the visual image.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, wherein the intensity value is a color intensity value.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, wherein the regions of interest are moving in relation to the flare burner.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, wherein the regions of interest are static in relation to the flare burner.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, further comprising adjusting at least one process condition of the processing plant based on a difference between the smoke index is at or above the threshold smoke index level; and, repeating steps a) - c).
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, wherein the at least one process condition is adjusted to maintain the smoke index at the predetermined set point.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, wherein steps a) - c) are repeated until the smoke index reaches a predetermined level.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, further comprising calculating a reliability value for each smoke index calculated.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, further comprising increasing a weighting to non-camera based values used for determining the smoke index based on the reliability values.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, further comprising obtaining a current process condition information of the processing plant; and, when a number of the calculated smoke indexes with a reliability value above a predetermined level is below a minimum amount, determining the apparent presence by comparing the current process condition information with a database having process condition data and apparent smoke probability associated with the process condition data.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, further composing obtaining a current atmospheric condition information at the flare burner; and, when a number of the calculated smoke indexes with a reliability value above a predetermined level is below a minimum amount, determining the apparent presence by comparing the atmospheric condition information with the database, wherein the database further comprises having atmospheric condition data and apparent smoke probability associated with the atmospheric condition data.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, further comprising obtaining an audio signature of the flare burner corresponding to the visual image, and wherein the smoke index for each regions of interest is calculated based on the audio signature.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, further comprising obtaining an UV image of the flare burner corresponding to the visual image, and wherein the smoke index for each regions of interest is calculated based on the UV image.
  • An embodiment of the invention is one, any or all of prior embodiments in this paragraph up through the first embodiment in this paragraph, further comprising obtaining a temperature at a predetermined position spaced from the flare burner corresponding to the visual image; comparing the temperature to a threshold temperature; and, performing an action when the temperature meets or passes the threshold temperature.
  • a second embodiment of the invention is a process for determining an apparent presence or absence of smoke from a flare burner associated with a processing plant, the process comprising obtaining a plurality of visual images of the flare burner and an area surrounding the flare burner, wherein the plurality includes an image with no smoke and an image with smoke, and wherein the presence or absence of smoke has been predetermined; analyzing the visual image by segmenting the visual image into a plurality of regions of interest; and, calculating a smoke index for each of the regions of interest based on a historical intensity of a plurality of pixels within each of the regions of interest; and, determining the apparent presence of smoke based on the smoke index for the regions of interest by comparing the smoke index to a threshold smoke index level; and, comparing the determination with the predetermined presence or absence of smoke with the image.
  • a third embodiment of the invention is a system for process for monitoring a flare burner associated with a processing plant and configured to receive a gas to be combusted, the system configured to determine an apparent presence or absence of smoke from the flare burner, the system comprising at least one camera configured to obtain images of the flare burner and an area surrounding the flare burner; and, a controller in communication with the camera and configured to receive the visual image of the flare burner; and, analyze the visual image by segmenting the visual image into a plurality of regions of interest; and, calculating a smoke index for each of the regions of interest based on a historical intensity of a plurality of pixels within each of the regions of interest; determine the apparent presence of smoke based on the smoke index for the regions of interest by comparing the smoke index to a threshold smoke index level; and, indicate the apparent presence of smoke for the regions of interest when the smoke index is at or above the threshold smoke index level.

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Environmental & Geological Engineering (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

La présente invention concerne des procédés et des systèmes destinés à surveiller un brûleur de torche avec une caméra. Les procédés et les systèmes peuvent indiquer à des opérateurs la présence ou l'absence d'un ou de plusieurs éléments parmi de la fumée, une flamme de torche et un panache de vapeur et enregistrer ces indications ou mesures. De plus, les procédés et les systèmes peuvent confirmer si oui ou non une conformité avec des réglementations locales sur des émissions visuelles, un panache de fumée est obtenue. Les procédés et systèmes ajustent automatiquement le taux de délivrance d'entrées clé comprenant des mesures d'assistance au gaz combustible, au gaz de purge, à la vapeur et/ou à l'air simultanément pour maintenir ou obtenir la conformité avec lesdites exigences réglementaires locales. La présente invention concerne également des procédés pour un processus d'apprentissage automatique destiné à utiliser des entrées de dispositif de commande pour identifier des états de torche normaux et anormaux et fournir des indications visuelles et des recommandations d'opération de torche.
PCT/US2020/036169 2019-06-07 2020-06-04 Procédés et systèmes permettant d'analyser des images d'un brûleur de torche WO2020247664A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201962858707P 2019-06-07 2019-06-07
US62/858,707 2019-06-07

Publications (1)

Publication Number Publication Date
WO2020247664A1 true WO2020247664A1 (fr) 2020-12-10

Family

ID=73649991

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2020/036169 WO2020247664A1 (fr) 2019-06-07 2020-06-04 Procédés et systèmes permettant d'analyser des images d'un brûleur de torche

Country Status (2)

Country Link
US (1) US11519602B2 (fr)
WO (1) WO2020247664A1 (fr)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112781942A (zh) * 2020-12-16 2021-05-11 中国辐射防护研究院 一种爆炸气溶胶源项获取和环境监测方法
US12072097B2 (en) 2021-03-29 2024-08-27 Honeywell International Inc. Active and passive combustion stabilization for burners for highly and rapidly varying fuel gas compositions
US11649960B2 (en) 2021-04-02 2023-05-16 Honeywell International Inc. Low NOx burner with bypass conduit
WO2022217208A1 (fr) * 2021-04-05 2022-10-13 Baker Hughes Holdings Llc Surveillance et régulation d'émission de systèmes de torche
WO2022217259A1 (fr) * 2021-04-07 2022-10-13 Schlumberger Technology Corporation Optimisation de torche en temps réel au moyen d'un dispositif périphérique
CN114562252A (zh) * 2022-03-07 2022-05-31 中石化胜利石油工程有限公司塔里木分公司 一种气井井喷着火情况下的地层压力反演系统与反演方法
US20240011632A1 (en) * 2022-07-07 2024-01-11 Saudi Arabian Oil Company Monitoring and maintaining flare tip temperatures
US20240103497A1 (en) * 2022-09-22 2024-03-28 Sensia Netherlands B.V. Systems and methods for uncertainty measurement and reporting for emissions
CN115619355B (zh) * 2022-11-30 2023-03-21 成都秦川物联网科技股份有限公司 智慧燃气有害组分监控方法、物联网系统、装置以及介质
CN117058161B (zh) * 2023-10-12 2024-02-20 深圳市五轮科技股份有限公司 基于图像处理的电子烟雾化烟雾图像分割方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4266535B2 (ja) * 2001-04-27 2009-05-20 株式会社シー・イー・デー・システム 黒煙検知システム
EP2309186A2 (fr) * 2009-10-07 2011-04-13 John Zink Company, L.L.C. Système de détection d'image, logiciel, appareil et procédé de contrôle d'un équipement de combustion
US8138927B2 (en) * 2007-03-22 2012-03-20 Honeywell International Inc. Flare characterization and control system
US20170116499A1 (en) * 2014-03-28 2017-04-27 Nec Corporation Detection device, detection method, and program recording medium

Family Cites Families (47)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19632174C2 (de) 1996-08-09 2002-02-07 Abb Research Ltd Temperaturmessverfahren
US7505608B2 (en) 2005-04-15 2009-03-17 The Boeing Company Methods and apparatus for adaptive foreground background analysis
US8653461B1 (en) 2007-03-23 2014-02-18 Flir Systems, Inc. Thermography camera tuned to detect absorption of infrared radiation in a selected spectral bandwidth
US7687776B2 (en) 2007-04-11 2010-03-30 General Monitors, Inc. Gas and/or flame imaging system with explosion proof housing
US7876229B2 (en) 2007-08-14 2011-01-25 Honeywell International Inc. Flare monitoring
WO2009087614A2 (fr) 2008-01-08 2009-07-16 Opgal Optronic Industries Ltd. Système et procédé de détection de fuite de gaz
US20120239330A1 (en) 2010-01-18 2012-09-20 Pierre Tremblay Radiometric calibration method for infrared detectors
US9121760B2 (en) 2010-01-27 2015-09-01 Ci Systems Ltd. Room-temperature filtering for passive infrared imaging
WO2011100225A1 (fr) 2010-02-09 2011-08-18 Conocophillips Company Contrôle automatisé de torche
WO2011138766A1 (fr) 2010-05-07 2011-11-10 Telops Inc. Système et procédé permettant de mesurer à distance la carte de vitesse directionnelle d'émissions gazeuses
US9250135B2 (en) 2011-03-16 2016-02-02 Honeywell International Inc. MWIR sensor for flame detection
US8841617B2 (en) 2011-07-05 2014-09-23 Honeywell International Inc. Flame detectors and methods of detecting flames
US9587987B2 (en) 2012-03-12 2017-03-07 Honeywell International Inc. Method and device for detection of multiple flame types
US9599508B2 (en) 2012-05-18 2017-03-21 Rebellion Photonics, Inc. Divided-aperture infra-red spectral imaging system
CA2873989C (fr) 2012-05-18 2022-05-17 Rebellion Photonics, Inc. Systeme d'imagerie spectrale infrarouge a ouverture divisee pour detection chimique
US9258495B2 (en) 2012-06-21 2016-02-09 Providence Photonics, Llc Multi-spectral infrared imaging system for flare combustion efficiency monitoring
US9225915B2 (en) 2012-07-06 2015-12-29 Providence Photonics, Llc Calibration and quantification method for gas imaging camera
US20140184793A1 (en) 2012-12-31 2014-07-03 Honeywell International Inc. Multispectral flame detector
US10191022B2 (en) 2013-03-15 2019-01-29 Uvia Group Llc Gas imager employing an array imager pixels with order filters
US20140336953A1 (en) * 2013-05-13 2014-11-13 National Research Council Of Canada Method to quantify emission rates in atmospheric plumes
US9127891B2 (en) 2013-07-10 2015-09-08 Honeywell International, Inc. Furnace visualization
US9562849B2 (en) 2013-11-12 2017-02-07 Rebellion Photonics, Inc. Divided-aperture infra-red spectral imaging system
US10041672B2 (en) 2013-12-17 2018-08-07 Schlumberger Technology Corporation Real-time burner efficiency control and monitoring
US9212851B2 (en) 2014-02-10 2015-12-15 Honeywell International Inc. Multi resolution, hierarchical radiance field estimation
US9594359B2 (en) 2014-04-14 2017-03-14 Honeywell International Inc. Feedback control for reducing flaring process smoke and noise
US20150355030A1 (en) 2014-06-04 2015-12-10 Honeywell International Inc. Equipment and method for intensity-temperature transformation of imaging system
US9196032B1 (en) 2014-06-04 2015-11-24 Honeywell International Inc. Equipment and method for three-dimensional radiance and gas species field estimation
US9664568B2 (en) 2014-06-16 2017-05-30 Honeywell International Inc. Extended temperature mapping process of a furnace enclosure with multi-spectral image-capturing device
US9696210B2 (en) 2014-06-16 2017-07-04 Honeywell International Inc. Extended temperature range mapping process of a furnace enclosure using various device settings
IL236593A0 (en) 2014-07-24 2015-10-29 Opgal Optronic Ind Ltd High precision infrared measurements
US10182195B2 (en) 2014-09-23 2019-01-15 Flir Systems, Inc. Protective window for an infrared sensor array
US9702555B2 (en) 2014-10-07 2017-07-11 Honeywell International Inc. Equipment and method for furnace visualization using virtual interactive windows
US20160097680A1 (en) 2014-10-07 2016-04-07 Honeywell International, Inc. Equipment and method for advanced imaging burner control process
US9651254B2 (en) * 2014-10-24 2017-05-16 Lumasense Technologies Holdings, Inc. Measuring and controlling flame quality in real-time
WO2016073537A1 (fr) 2014-11-04 2016-05-12 Flir Surveillance, Inc. Structure sélective de longueur d'onde multibande
US9581543B2 (en) 2014-11-10 2017-02-28 Ci Systems (Israel) Ltd. Infrared detection and imaging device with no moving parts
US9759611B2 (en) 2014-12-07 2017-09-12 Ci Systems (Israel) Ltd. Dual spectral imager with no moving parts
US9876968B2 (en) 2014-12-08 2018-01-23 Ci Systems (Israel) Ltd. Drift correction method for infrared imaging device
US9726543B2 (en) 2015-02-18 2017-08-08 Providence Photonics, Llc Apparatus and method for validating leak survey results
WO2016139261A1 (fr) 2015-03-02 2016-09-09 Flir Systems Ab Imagerie de gaz par infrarouge passif basée sur la bande de longueur d'onde
EP3265996B1 (fr) 2015-03-02 2024-07-17 Flir Systems AB Quantification de gaz en imagerie de gaz optique passive
CN112161947B (zh) 2015-03-19 2024-10-15 Ci系统(以色列)股份有限公司 减少由改变至少一环境特征引起的漂移的方法
US20180136072A1 (en) 2015-07-16 2018-05-17 Ci Systems (Israel) Ltd. Gas detection, imaging and flow rate measurement system
WO2017058832A1 (fr) 2015-09-28 2017-04-06 Schlumberger Technology Corporation Systèmes de surveillance et de commande de brûleur
US9970756B2 (en) 2015-10-06 2018-05-15 Bridger Photonics, Inc. High-sensitivity gas-mapping 3D imager and method of operation
US10043288B2 (en) 2015-11-10 2018-08-07 Honeywell International Inc. Methods for monitoring combustion process equipment
US10746400B2 (en) 2016-06-28 2020-08-18 General Electric Company Integrated flare combustion control

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4266535B2 (ja) * 2001-04-27 2009-05-20 株式会社シー・イー・デー・システム 黒煙検知システム
US8138927B2 (en) * 2007-03-22 2012-03-20 Honeywell International Inc. Flare characterization and control system
EP2309186A2 (fr) * 2009-10-07 2011-04-13 John Zink Company, L.L.C. Système de détection d'image, logiciel, appareil et procédé de contrôle d'un équipement de combustion
US20170116499A1 (en) * 2014-03-28 2017-04-27 Nec Corporation Detection device, detection method, and program recording medium

Also Published As

Publication number Publication date
US11519602B2 (en) 2022-12-06
US20200386404A1 (en) 2020-12-10

Similar Documents

Publication Publication Date Title
US11519602B2 (en) Processes and systems for analyzing images of a flare burner
CA3081967C (fr) Procede et systeme pour analytique de poussee avancee de reseau
AU2008228846B2 (en) A flare characterization and control system
CN110084092B (zh) 用机器学习算法进行温度测量的方法和系统
US20230120460A1 (en) Method of assessment of the quality of the burn of the gases in the flare and adjustment to the vapor flow rate in a continuous and constant way
EP3874202A1 (fr) Système d'analyse de flamme
US11188047B2 (en) Automatic visual and acoustic analytics for event detection
CN1406366A (zh) 视频烟雾检测系统
WO2018043417A1 (fr) Dispositif d'évaluation de tuyauterie, procédé d'évaluation de tuyauterie et programme d'évaluation de tuyauterie
KR101044903B1 (ko) 영상 감시 시스템에서 은닉 마르코프 모델을 이용한 불 검출방법
CN100487437C (zh) 基于图像处理的烟气排放连续监测系统
EP3748444B1 (fr) Procédé et système pour une analyse d'éruption avancée connectée
CN116712697A (zh) 水喷雾灭火系统及方法
JP6604446B2 (ja) ガス状態判別方法とそれに用いる画像処理装置及び画像処理プログラム
CN117475366A (zh) 一种基于深度学习的危废库火灾风险监控系统
TWI381139B (zh) 基於影像之燃燒製程監控與診斷方法及其相關之電腦可讀取媒體
KR20230096464A (ko) 영상분석 기반 안전 모니터링 방법
Jangale et al. Deep Learning based Flare Image Analytics for Emissions Monitoring at the Edge
KR100627483B1 (ko) 화상 이미지 분석을 통한 배출매연 인식 및 경보장치 및방법
KR100711364B1 (ko) 화상 이미지 분석을 통한 배출매연 인식 및 자동경보 장치및 방법
KR100680114B1 (ko) 색영상을 이용한 조명과 주변환경에 강건한 화재감지장치와그 방법 및 그 기록매체
KR100554759B1 (ko) 화상 이미지 분석을 통한 배출매연 인식 및 경보방법
KR20240138377A (ko) 영상분석 기반 화재 및 연기 감지 방법
WO2024057051A1 (fr) Procédé et dispositif d'estimation de valeur d'efficacité de combustion pendant le torchage
Martinez Development of a plume identification algorithm for optical gas imaging of natural gas emissions that requires no human intervention

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20818553

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 02/05/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20818553

Country of ref document: EP

Kind code of ref document: A1